Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 44 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4931. Min Act: -0.0001

Data Index: 322581 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4447. Min Act: -0.0001

Data Index: 478687 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3386. Min Act: -0.0001

Data Index: 111933 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3536. Min Act: -0.0001

Data Index: 1187600 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3673. Min Act: -0.0001

Data Index: 397929 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3619. Min Act: -0.0001

Data Index: 723547 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1275997 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3588. Min Act: -0.0001

Data Index: 206177 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3081. Min Act: -0.0001

Data Index: 322322 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3190. Min Act: -0.0001

Data Index: 513161 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.2962. Min Act: -0.0001

Data Index: 771706 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3347. Min Act: -0.0001

Data Index: 713446 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3013. Min Act: -0.0001

Data Index: 483136 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3073. Min Act: -0.0001

Data Index: 424981 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3046. Min Act: -0.0001

Data Index: 203358 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1120058 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3141. Min Act: -0.0001

Data Index: 122620 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.2911. Min Act: -0.0001

Data Index: 202023 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.2905. Min Act: -0.0001

Data Index: 524208 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3026. Min Act: -0.0001

Data Index: 474618 (C4 (Web Text))

Max Activating Token Index: 54